Beyond Anthropomorphism: Enhancing Grasping and Eliminating a Degree of Freedom by Fusing the Abduction of Digits Four and Five
Simon Fritsch, Liam Achenbach, Riccardo Bianco, Nicola Irmiger, Gawain Marti, Samuel Visca, Chenyu Yang, Davide Liconti, Barnabas Gavin Cangan, Robert Jomar Malate, Ronan J. Hinchet, Robert K. Katzschmann
TL;DR
The paper tackles robust dexterous grasping under actuation and control constraints by introducing the SABD hand, a $16$-DoF anthropomorphic design that fuses the Add/Abd motion of digits four and five to create a large ROM and a non-anthropomorphic grasp envelope. This approach yields a substantial workspace expansion (up to $400\%$ for the fused digits) and enables very large object grasping (up to $200\,\mathrm{mm}$ side distance) while maintaining manipulation capabilities; the thumb’s palm-deformation and opposition capabilities further enhance grasp versatility. Model-based analysis and extensive experiments—workspace evaluation, pinch-nullspace assessment, teleoperation on YCB objects with an $86\%$ success rate, and reinforcement-learning-based stability studies—validate that the combined abduction design improves grasp stability and flexibility without excessive mechanical complexity. Overall, the SABD hand offers a practical compromise between minimal actuators and high dexterity, with clear directions for improving tendon routing and proprioceptive sensing to fully exploit its potential in real-world manipulation tasks.
Abstract
This paper presents the SABD hand, a 16-degree-of-freedom (DoF) robotic hand that departs from purely anthropomorphic designs to achieve an expanded grasp envelope, enable manipulation poses beyond human capability, and reduce the required number of actuators. This is achieved by combining the adduction/abduction (Add/Abd) joint of digits four and five into a single joint with a large range of motion. The combined joint increases the workspace of the digits by 400% and reduces the required DoFs while retaining dexterity. Experimental results demonstrate that the combined Add/Abd joint enables the hand to grasp objects with a side distance of up to 200 mm. Reinforcement learning-based investigations show that the design enables grasping policies that are effective not only for handling larger objects but also for achieving enhanced grasp stability. In teleoperated trials, the hand successfully performed 86% of attempted grasps on suitable YCB objects, including challenging non-anthropomorphic configurations. These findings validate the design's ability to enhance grasp stability, flexibility, and dexterous manipulation without added complexity, making it well-suited for a wide range of applications. A supplementary video is available at https://youtu.be/P3jRts46o4s .
